Spaces:
Runtime error
Runtime error
File size: 2,861 Bytes
737b074 8c25a54 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load NVLM-D-72B model and tokenizer
# model_name = "nvidia/NVLM-D-72B"
model_name = "nvidia/NVLM-D-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_name,
trust_remote_code=True,
device_map="auto"
)
# Inference function
def generate_response(prompt, max_tokens=50):
inputs = tokenizer(prompt, return_tensors="pt").to("cuda") # Adjust to "cpu" if GPU unavailable
outputs = model.generate(**inputs, max_new_tokens=max_tokens)
return tokenizer.decode(outputs[0])
# Gradio interface
interface = gr.Interface(
fn=generate_response,
inputs=[
gr.Textbox(lines=2, label="Enter your prompt"),
gr.Slider(10, 100, step=10, value=50, label="Max Tokens")
],
outputs="text",
title="NVIDIA NVLM-D-72B Demo",
description="Generate text using NVIDIA's NVLM-D-72B model."
)
if __name__ == "__main__":
interface.launch()
# import gradio as gr
# from huggingface_hub import InferenceClient
# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
# def respond(
# message,
# history: list[tuple[str, str]],
# system_message,
# max_tokens,
# temperature,
# top_p,
# ):
# messages = [{"role": "system", "content": system_message}]
# for val in history:
# if val[0]:
# messages.append({"role": "user", "content": val[0]})
# if val[1]:
# messages.append({"role": "assistant", "content": val[1]})
# messages.append({"role": "user", "content": message})
# response = ""
# for message in client.chat_completion(
# messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = message.choices[0].delta.content
# response += token
# yield response
# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = gr.ChatInterface(
# respond,
# additional_inputs=[
# gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
# gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
# gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
# gr.Slider(
# minimum=0.1,
# maximum=1.0,
# value=0.95,
# step=0.05,
# label="Top-p (nucleus sampling)",
# ),
# ],
# )
# if __name__ == "__main__":
# demo.launch()
|